Calcupedia

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, covering the safety profile. The description adds useful context that the call is UI-driven rather than agent-driven, but says nothing about return values, side effects, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero filler, with the core operation and the routing constraint front-loaded. Nothing is repeated from the title or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an internal, non-assistant-facing tool the description does enough to route an agent away, and no output schema means return values need no explanation. But the two required parameters, including a nested object, are entirely undocumented anywhere, so the definition is not self-sufficient if the tool is ever invoked.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for both 'slug' and 'values', yet it mentions neither. Nothing explains what a slug identifies or what key/value pairs 'values' should contain (number-or-string, nested object), leaving a caller unable to construct a valid call from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Recalculates a calculator card.' This is clearly distinct from creating or listing calculators. However, it never contrasts itself with the sibling run_calculator, which sounds closely related, so the agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives both a trigger ('after the user changes a value') and an explicit exclusion ('Used by the card itself, not by the assistant'), which strongly steers an agent away. It does not name the alternative tool (run_calculator) that an assistant should use instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description nonetheless adds real behavioral context: customizing the calculator requires no account while creating the embed requires a free account. That account/prerequisite nuance is exactly the kind of information annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with the core purpose front-loaded, followed by supported platforms and the account prerequisite, then the usage trigger. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only tool with a fully documented schema and no output schema, the description supplies everything needed: what is returned, which platforms the embed targets, the account requirement, and the usage condition. Nothing material to correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: the single slug parameter is documented in the schema, including its source ("Calculator slug from search_calculators") and an example. The description adds no further parameter meaning, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource: returns the embed/style link for a Calcupedia calculator, including what the link enables (styling and getting embed code). This is unmistakably distinct from the sibling tools calculate, run_calculator and search_calculators, all of which do something other than produce an embed link.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use it when someone wants a calculator on their website, blog or online store" gives a clear triggering condition. It does not explicitly name the sibling tools as alternatives or state when NOT to use it, so it stops short of the top score, but the routing intent is clear enough for an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real behavioral value beyond that: it discloses the return payload (results, a shareable link, accepted inputs with current values) and the default-filling behavior for omitted inputs. It is silent on error handling for unknown slugs or invalid input keys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, all load-bearing, with the core action stated first and the return payload, usage scope and input-key convention following in priority order. No filler or restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, but the description itself enumerates the return contents, so the agent knows what comes back. For a two-parameter tool with full schema coverage and full annotation coverage, nothing needed to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine semantics: input keys vary per calculator, they are discoverable via search_calculators, and omitted inputs fall back to the calculator's defaults. That is information the schema cannot express.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Runs one Calcupedia calculator with its verified formulas') and scopes the domain (finance, health, math, date, unit conversion). It also distinguishes itself from search_calculators by noting that tool lists the input keys this one consumes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear condition for use ('questions that need exact figures the user can check') and points to search_calculators as the source of input keys. It does not, however, explain how it differs from the sibling 'calculate' tool, leaving an obvious overlap unresolved.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as a safe, idempotent, read-only, closed-world search, so the safety profile is covered. The description adds real behavioral context beyond that: the result shape (slug, category, page link) and the notable quirk that only the top 3 results include input keys, defaults and allowed values — information an agent needs before chaining into run_calculator.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with verb, resource and corpus size, then return shape, then usage — a logical order with no filler sentences. It is somewhat dense with parenthetical example lists, which slightly burdens readability but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description correctly compensates by describing what results contain and how the top-3 enrichment enables chaining. Combined with annotations covering the safety profile, an agent has everything needed to call it correctly and act on the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both 'query' and 'limit' are already documented in the schema, establishing a baseline of 3. The keyword examples ('mortgage', 'bmi', 'kg to lbs') are helpful illustrations of query format but add no constraint or syntax detail beyond what the schema states, and 'limit' is not discussed at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Searches Calcupedia's 2,400+ calculators and unit converters by keyword') and scopes the corpus precisely. It is immediately distinguishable from siblings like run_calculator and calculate, which execute rather than locate calculators.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit triggers ('when the user wants a number worked out ... a loan, interest, savings, tax, salary, BMI, calories, date or age, percentage or unit conversion') and routes to the next step: 'then pass the slug to run_calculator.' The alternative (run_calculator) is named with the condition that selects it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.